You're looking at a specific version of this model. Jump to the model overview.
annakaz /sdxl-inference:ef7910f4
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| lora_1 |
string
|
https://replicate.delivery/pbxt/TJLLieDQVNWfM0o2UOjh103bt1XJp1hV4fKjMtz17RAtBnZjA/trained_model.tar
|
URL of trained lora model
|
| prompt |
string
|
A full body Realistic portrait of TOK man.
Model gender: male,
Model ethnicity: Caucasian/Asian,
Model age: 20,
Hair style and color: short, straight and brown,
Eyes color: brown,
Dressing style: any,
Surrounding environment: a Jedi Knight, wielding a lightsaber, standing on a distant planet with a swirling galaxy background, and a red lightsaber glow in the foreground.,
Camera settings: cinematic, soft light, clean
|
Input prompt
|
| negative_prompt |
string
|
low quality, duplicate faces, deformed iris, distorted eyes, text, cropped, out of frame, jpeg artifacts, duplicate, mutilated, extra fingers, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, clone, disfigured, fused fingers
|
Input Negative Prompt
|
| enable_face_inpainting |
boolean
|
False
|
Inpaint small faces to improve resolution. Will slow down inference.
|
| face_inpainting_prompt |
string
|
<s0><s1> face. Model gender: female,
Model ethnicity: Caucasian
Model age: 25
Hair style and color: short, straight and brown,
Eyes color: brown
|
Face inpainting prompt
|
| face_inpainting_negative_prompt |
string
|
frame, mask, surgical, ui, ugly, distorted eyes, deformed iris, toothless, squint, deformed iris, deformed pupils, low quality, jpeg artifacts, ugly, mutilated
|
Face inpainting negative prompt
|
| max_face_inpaint_size |
integer
|
130
|
Max size of face to inpaint. Recommended: 100-280. If it's too high, may get weird portraits.
|
| inpainting_gradient_percent_size |
number
|
0.25
|
Percent edge to blur to make transition smoother. Recommended: 0.25
|
| inpainting_guidance_scale |
number
|
3.5
|
Guidance scale for inpainting. Recommended: 3.5
|
| inpainting_num_inference_steps |
integer
|
25
|
Inference steps inpainting. Recommended: 25
|
| inpainting_lora_scale |
number
|
0.9
Max: 1 |
LoRA additive scale for face. Recommended:0.8-0.95
|
| face_padding |
integer
|
0
|
How much to pad the face for inpainting. Recommended: 0-20
|
| image |
string
|
Input image for img2img or inpaint mode
|
|
| mask |
string
|
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
|
|
| width |
integer
|
768
|
Width of output image
|
| height |
integer
|
1024
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to output.
|
| scheduler |
string
(enum)
|
K_EULER
Options: DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM |
scheduler
|
| num_inference_steps |
integer
|
35
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| refine |
string
(enum)
|
no_refiner
Options: no_refiner, expert_ensemble_refiner, base_image_refiner |
Which refine style to use
|
| high_noise_frac |
number
|
0.8
Max: 1 |
For expert_ensemble_refiner, the fraction of noise to use
|
| refine_steps |
integer
|
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
|
|
| apply_watermark |
boolean
|
False
|
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
|
| lora_scale |
number
|
0.6
Max: 1 |
LoRA additive scale. Only applicable on trained models.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}